Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Image Quality Assessment Techniques Improve Training and Evaluation of Energy-Based Generative Adversarial Networks
Michael O. Vertolli, Jim Davies
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:We propose a new, multi-component energy function for energy-based Generative Adversarial Networks (GANs) based on methods from the image quality assessment literature. Our approach expands on the Boundary Equilibrium Generative Adversarial Network (BEGAN) by outlining some of the short-comings of the original energy and loss functions. We address these short-comings by incorporating an l1 score, the Gradient Magnitude Similarity score, and a chrominance score into the new energy function. We then provide a set of systematic experiments that explore its hyper-parameters. We show that each of the energy function's components is able to represent a slightly different set of features, which require their own evaluation criteria to assess whether they have been adequately learned. We show that models using the new energy function are able to produce better image representations than the BEGAN model in predicted ways.
TL;DR:Image Quality Assessment Techniques Improve Training and Evaluation of Energy-Based Generative Adversarial Networks
Keywords:generative adversarial networks, gans, deep learning, image modeling, image generation, energy based models
Enter your feedback below and we'll get back to you as soon as possible.